A tool for creating named custom identities for software agents and assigning them to agent sessions. Each identity can have a name, emoji, model choice, and default role within one of three predefined sizes.

Use it to list, add, remove, or assign custom agent identities.

It lets a team distinguish agents and give them a consistent role or appearance without changing the underlying size or site settings. Changes are confirmed before they take effect in the next session.

creatures — Skill for Claude Code by jerpint/woltspace

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add jerpint/woltspace --skill creatures

Clone the repo

git clone --depth 1 https://github.com/jerpint/woltspace

Made for: Claude Code.

Or install woltspace, the plugin that ships this one along with the rest of its 23 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jerpint/woltspace/creatures/github.svg)](https://agentmods.dev/skills/jerpint/woltspace/creatures)

Your own site

<a href="https://agentmods.dev/skills/jerpint/woltspace/creatures"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/creatures/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jerpint/woltspace/creatures"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/creatures.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 800 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.00800
Opus 5.5	$0.00024	$0.00320
Sonnet 5.5	$0.00012	$0.00160
Haiku 4.5	$0.00006	$0.00080

Measured 14d ago against content hash bb92238daa17, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

creatures scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

container/skills/creatures/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creatures: register one, or change a wolt's

The lodge has three sizes: 🦦 otter (quick), 🦫 beaver (builder) and 🦝 raccoon (thinker). A custom creature is a new identity on one of them: its own name and emoji, optionally its own model per engine and a default role. It behaves exactly like its size: the same site, tier and lore. Only the name and emoji change, everywhere the lodge shows a wolt (Telegram, Slack, the lodge, the TUI, its site).

Custom creatures live in the lodge's settings. Change them only with the commands below, never by editing woltspace.json or a wolt.json by hand.

Always confirm first

Before you register, remove or assign a creature, tell the user exactly what will change and wait for a yes. That includes changing your own creature. For example:

I'll register ⭐ star (raccoon-sized, codex model gpt-6-astra) and make alpha a star. Its next session will show ⭐; this session stays as it is. Go?

Commands

woltspace creature list                     # the sizes and the lodge's custom creatures
woltspace creature add star --emoji ⭐ --size raccoon \
  --model codex=gpt-6-astra --role "Reviewer and planner"
woltspace creature assign alpha star        # change a wolt's creature
woltspace creature rm star                   # only when no wolt is one

name: lowercase letters, digits and hyphens. Built-in names (raccoon, wolf, dog, ...) are taken.
--size: what it behaves like: otter, beaver or raccoon.
--model HARNESS=MODEL: optional, repeatable. The id must be one the engine offers (GET /harnesses lists them). An engine without one uses the size's default.
--role: optional. The default role for a new wolt of this creature.
add never overwrites: to change a creature, rm it (no wolt may be one) and add it again.

What assign changes, and when

woltspace creature assign <wolt> <type> changes only the wolt's creature type. It prints what the wolt keeps:

Its own pins win. A model or harness set on the wolt itself stays and still applies. Then comes the creature's own model, then the size's default.
Its role stays. A creature's role is only a default for new wolts.
Next session. A running session keeps the model and settings it started with. Tell the user the change shows from the wolt's next session.
A starter site that still shows the old creature's emoji switches to the new one. A site emoji the wolt chose itself stays.

Read the full file on GitHub · 69 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

14d ago First seen · 69 lines · 59 tokens per session scan A bb92238daa17

Subscribe to this mod's changes

creatures is a skill published in the GitHub repository jerpint/woltspace (22 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 800 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-28.

Building agents

creatures next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
creaturesjerpint/woltspace	Skill	22	yesterday	MIT	A	59	Claude Code
imagegenopenai/codex	Skill	135k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	316k	7d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code